#general
Jul 26July 27, 2026
Hi, been having this repeated challenge for hours now, even after changing models, see debug error (tried to de-auto-select model but not activating)
Your conversation is too long. Please start a new chat or remove some messages.
Agent: My Assistant
Model: 3cbf7cf2-a4d6-4f99-b73a-348801f7****
Provider: groq
Model source: auto-selected (best available)
Code: contexttoolong
Provider: groq
Status: 413
Type: apipayloadtoolargeerror
Message: Request too large for model
llama-3.3-70b-versatile in organization org_01kxd8hjn4f7vtzgf55x2e48x9 service tier on_demand on tokens per minute (TPM): Limit 12000, Requested 35421, please reduce your message size and try again. Need more tokens? Upgrade to Dev Tier today at console.groq.com/settings/billingRaw Error:
{
"url": "localhost/v1/groq/β¦/completions",
"statusCode": 413,
"isRetryable": false,
"responseBody": {
"error": {
"message": "Request too large for model
llama-3.3-70b-versatile in organization org_01kxd8hjn4f7vtzgf55x2e48x9 service tier on_demand on tokens per minute (TPM): Limit 12000, Requested 35421, please reduce your message size and try again. Need more tokens? Upgrade to Dev Tier today at console.groq.com/settings/billing", "type": "apipayloadtoolargeerror"
}
}
}
Session: c540c217-e47a-423c-a3a3-11998a0b718a
Trace: e8744659ee4413956dbe0ed71e30c13b
Span: 08758220ccd7eafe
Hi, I only have a RuPay card, and both OpenRouter and OpenAI reject it with "This card type isn't accepted." Gemini now requires prepaid credits in my region. Is there a hackathon API key, sponsored credits, or another recommended provider that participants with RuPay cards can use?
Hi! I have a quick question regarding the submission. Are we allowed to include a voice-over narration in our demo video to explain the project and workflow, or is the submission expected to be screen recording only?
Thank you!
Hey guys! Iβve been testing out Archestra for a week. The main things I want to get working is to provide shared/curated skills with the rest of my team and provide them a way to share internal vibe-coded apps (I understand the feature is still in beta, I have some feedback that Iβd love to share!). While testing some skills, in particular skills involving creating some HTML assets, I noticed that my agent uses
archestra__run_command to write files. Problem with that is that I always hit a Error: command is too large (> 16384 bytes) error, and it forces the agent to unreliably find workarounds (once it tried rewriting the HTML file in small splits, forcing the content to be rewritten in small pages and links between them, another time it just zipped everything). I got the same when working with Apps, even more brutally given that, well, itβs all about apps. Is my agent misconfigured or is this a current limitation of Archestra?
hey .. actually I got another issue .. after stopping the record and saving the prompt and so on when I try to download it it just says it will be exported once it's ready and you download it but nothing got out to be saved on my device and when I try to submit the thing it says sign in to github and once I press it another screen shows that I didn't define the prompt or whatever even tho that I chose the chat messages about the prompt and cut the recording to 30 secs ... is that normal and is it happening with all or I'm missing smth ?
Hi! I'm blocked by what appears to be an Archestra issue.
In a fresh session, even sending "Hello" fails with:
context_too_longGroq reports ~40,000 requested tokens despite the prompt being only a few characters.
Example:
Request too large for model llama-3.1-8b-instant. Requested 40280 tokens.Has anyone seen this before or is there a way to clear/reset the app context?
When starting a conversation with a model like Gemini, for example, can't I switch to another one, like OpenAI's?
Read-only live mirror of Archestra.AI Slack
πJoin the discussion withAI enthusiasts!hey .. actually I got another issue .. after stopping the record and saving the prompt and so on when I try to download it it just says it will be exported once it's ready and you download it but nothing got out to be saved on my device and when I try to submit the thing it says sign in to github and once I press it another screen shows that I didn't define the prompt or whatever even tho that I chose the chat messages about the prompt and cut the recording to 30 secs ... is that normal and is it happening with all or I'm missing smth ?
11 replies
Ah I see the issue! The "Recording incomplete" dialog says *"This recording has no description or build prompt yet" β it looks like even though you selected chat messages, they weren't saved as the build prompt. Try this: 1. In the player, click "Try again" 2. Make sure to explicitly add a description* (the text field at top) 3. For the build prompt, after selecting messages, look for a save/confirm button The download taking time is normal β it renders the video first. But the submission blocker is definitely the missing prompt/description. If it keeps failing, there's also a manual submission option: "Learn how to submit your demo manually" link in that dialog. π€ Slack Agent
@user might be able to help
Hi @user! May I ask you to update to the latest version of Archestra and retry? Please LMK how it goes and sorry for the inconvenience π
Looks like you're still hitting that "Recording incomplete" error after trying again. Mark asked you to update to the latest Archestra version β I notice the orange "Update" button in the top right of your screenshots. Try clicking that to update first, then retry the recording flow! π€ Slack Agent
still the same it's saying it'll be downloaded once done but nothing is being downloaded
I see the orange "Update" button is still showing in the top right β looks like the update wasn't applied yet. Try clicking it, let it restart, then retry. If the download still doesn't work after updating, check your browser's download settings (sometimes downloads go to a different folder or get blocked). You can also try the manual submission route via that "Learn how to submit your demo manually" link. π€ Slack Agent
If you mean you've tried to download video of your recording, then it might take up to a few minutes to process the raw recording files into a video file in the background and only then download will start in the browser.
In practice I haven't seen yet video processing times longer than 3 minutes. While video is processing you should a see a toast with progress indication and "Cancel" button. If the toast won't appear, or it simply disappears without starting a download, then it is an issue.
Thanks. I'm on 1.3.18 now. Tried the download again and watched for the toast, there is toast appearing and disappearing after a while and I believe it starts the download and then disappears and then another ones says you can wait till the thing is downloaded it'll take few mins .. but nothing happens. Separately, the bigger blocker for me is the submit step saying the recording has no description or build prompt, even after I select the chat messages. Is there a save step for the build prompt I'm missing? cz of that I'm going to the downloading of the thing and then submitting manually but it's not downloading eventually π
I notice you're still on an older version β the orange "Update" button is visible in the top right corner of both screenshots. You mentioned 1.3.18 but it looks like there's a newer version available. Please click that Update button and restart first! For the build prompt issue: after clicking "Try again" and selecting chat messages, you should see a *"Save" or "Done"* button to confirm your selection β make sure you're clicking that before attempting to submit. If that button isn't appearing or isn't working, that's a bug worth reporting to Mark. π€ Slack Agent